{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T11:34:12Z","timestamp":1766748852578,"version":"3.37.3"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/jstsp.2017.2752462","type":"journal-article","created":{"date-parts":[[2017,9,14]],"date-time":"2017-09-14T18:13:48Z","timestamp":1505412828000},"page":"1254-1264","source":"Crossref","is-referenced-by-count":16,"title":["End-to-End Neural Segmental Models for Speech Recognition"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2445-2605","authenticated-orcid":false,"given":"Hao","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4005-679X","authenticated-orcid":false,"given":"Liang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingpeng","family":"Kong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Gimpel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karen","family":"Livescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chris","family":"Dyer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noah A.","family":"Smith","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steve","family":"Renals","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1298"},{"key":"ref38","article-title":"Lecture 6.5-RMSprop: Divide the gradient by a running average of its recent magnitude","author":"tieleman","year":"2012","journal-title":"Neural Netw Mach Learning"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(88)90053-2"},{"key":"ref32","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop Autom Speech Recog Underst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref30","article-title":"Multi-task learning with CTC and segmental CRF for speech recognition","volume":"abs 1702 6378","author":"lu","year":"2017","journal-title":"CoRR"},{"key":"ref37","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref36","article-title":"Recurrent neural network regularization","volume":"abs 1409 2329","author":"zaremba","year":"2014","journal-title":"CoRR"},{"key":"ref35","article-title":"Simplifying long short-term memory acoustic models for fast training and decoding","author":"miao","year":"2015","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639137"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390205"},{"key":"ref27","article-title":"A comparison of training approaches for discriminative segmental models","author":"tang","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495106"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1976.10159"},{"key":"ref20","article-title":"Semi-Markov conditional random fields for information extraction","volume":"17","author":"sarawagi","year":"2004","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","article-title":"Segmental recurrent neural networks","author":"kong","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2227734"},{"key":"ref24","first-page":"269","article-title":"Finite-state transducers in language and speech processing","volume":"23","author":"mohri","year":"1997","journal-title":"Comput Linguist"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846309"},{"key":"ref25","first-page":"321","article-title":"Semiring frameworks and algorithms for shortest-distance problems","volume":"7","author":"mohri","year":"2002","journal-title":"J Autom Lang Comb"},{"key":"ref50","article-title":"Segmental conditional random fields with deep neural networks as acoustic models for first-pass word recognition","author":"he","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref51","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-546"},{"key":"ref56","article-title":"Neural speech recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition","author":"soltau","year":"2016","journal-title":"CoRR"},{"key":"ref55","article-title":"Word embeddings for speech recognition","author":"bengio","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref54","article-title":"Word-level acoustic modeling with convolutional vector regression","author":"maas","year":"2012","journal-title":"Proc ICML Workshop on Representation Learning"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1038"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1997-427","article-title":"Hierarchical duration modelling for speech recognition using the ANGIE framework","author":"chung","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415088"},{"key":"ref40","article-title":"Inverted HMM—A proof of concept","author":"doetsch","year":"2016","journal-title":"Proc NIPS 2016 End-to-end Learn Speech Audio Process Workshop"},{"key":"ref12","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1–1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI\/Recon Technical Report"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S0885-2308(03)00006-8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288835"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-515","article-title":"Efficient segmental conditional random fields for phone recognition","author":"he","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2013-455","article-title":"Deep segmental neural networks for speech recognition","author":"abdel-hamid","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404845"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-40"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/89.536930"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2248112"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1983.4767370"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266447"},{"key":"ref5","article-title":"Speech recognition using SVMs","author":"smith","year":"2001","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168281"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.894524"},{"key":"ref49","article-title":"Sequence transduction with recurrent neural networks","volume":"abs 1211 3711","author":"graves","year":"2012","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372916"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref45","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.1186\/s13636-015-0068-3","article-title":"Phone recognition with hierarchical convolutional deep maxout networks","volume":"2015","author":"t\u00f3th","year":"2015","journal-title":"EURASIP J Audio Speech Music Process"},{"article-title":"Segmental models with an exploration of acoustic and lexical grouping in automatic speech recognition","year":"2015","author":"he","key":"ref41"},{"key":"ref44","article-title":"Wav2letter: An end-to-end convnet-based speech recognition system","volume":"abs 1609 3193","author":"collobert","year":"2016","journal-title":"CoRR"},{"key":"ref43","article-title":"Heterogeneous measurements and multiple classifiers for speech recognition","author":"halberstadt","year":"1998","journal-title":"Proc Int Conf Spoken Lang Process"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/8103432\/08037994.pdf?arnumber=8037994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T23:32:06Z","timestamp":1719444726000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8037994\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":57,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2017.2752462","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"type":"print","value":"1932-4553"},{"type":"electronic","value":"1941-0484"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}